Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5080 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.9214. Min Act: -0.1700
Data Index: 4163775 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.7027. Min Act: -0.1700
Data Index: 122279 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.6402. Min Act: -0.1700
Data Index: 3376406 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.5464. Min Act: -0.1700
Data Index: 2462183 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.5464. Min Act: -0.1700
Data Index: 3522627 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.5152. Min Act: -0.1700
Data Index: 1153888 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.4839. Min Act: -0.1700
Data Index: 2745641 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.4527. Min Act: -0.1700
Data Index: 1574758 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.5152. Min Act: -0.1700
Data Index: 7885478 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.4527. Min Act: -0.1700
Data Index: 7266118 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.4527. Min Act: -0.1700
Data Index: 1366859 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.4214. Min Act: -0.1700
Data Index: 52330 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.4214. Min Act: -0.1700
Data Index: 1304867 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.3902. Min Act: -0.1700
Data Index: 5525815 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.3902. Min Act: -0.1700
Data Index: 4013002 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.3902. Min Act: -0.1700
Data Index: 5861707 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.3589. Min Act: -0.1700
Data Index: 1668061 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.3902. Min Act: -0.1700
Data Index: 855572 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.3589. Min Act: -0.1700
Data Index: 8390171 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9214. Min Range: -6.9214
Max Act: 6.3277. Min Act: -0.1700
Data Index: 5636987 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19